AutoGen is an open-source framework from Microsoft Research for building multi-agent AI applications, where multiple LLM-powered agents converse, use tools, execute code, and collaborate to solve complex tasks through multi-turn conversations. It supports both fully autonomous and human-in-the-loop workflows, with customizable agent roles such as planners, coders, reviewers, and critics. AutoGen v0.4 introduced a redesigned asynchronous, event-driven architecture with improved observability and reusable components. As of 2026, the original AutoGen is in maintenance mode, with its ideas carried forward in the community AG2 fork and the new Microsoft Agent Framework.
Visit AutoGen's official website for product details and getting started.
Comprehensive guides and API references for using AutoGen.
Insights, updates, and use cases related to AutoGen and conversational AI.
Join the AutoGen community to discuss, share, and collaborate with other users and developers.
Access the source code, contribute, and find additional resources for AutoGen.